Intro to R_D5

Set RNotebook for Root Directory

Set Working Directory

rr setwd(~/Desktop/af-werx)

The working directory was changed to /Users/datasociety/Desktop/af-werx inside a notebook chunk. The working directory will be reset when the chunk is finished running. Use the knitr root.dir option in the setup chunk to change the working directory for notebook chunks.

Getting working Directory

rr getwd()

[1] \/Users/datasociety/Desktop/af-werx/data\

creating and setting the working directory

rr main_dir = ~/Desktop/af-werx
data_dir = paste0(main_dir, /data) data_dir

[1] \~/Desktop/af-werx/data\

rr plot_dir = paste0(main_dir, /plots) plot_dir

[1] \~/Desktop/af-werx/plots\

rr setwd(data_dir) getwd()

[1] \/Users/datasociety/Desktop/af-werx/data\

rr #load(_tables.RData) flights = nycflights13::flights

Static Plot Example

read data from data sample

CMP = read.csv("ChemicalManufacturingProcess.csv", header =  T, stringsAsFactors = F)

take a look at the data

View(CMP)

column_ids = c(1:4,14:16)
column_ids

[1]  1  2  3  4 14 15 16

display column ids and first few variables

CMP_subset = CMP[,column_ids]
str(CMP_subset)

'data.frame':   176 obs. of  7 variables:
 $ Yield                 : num  38 42.4 42 41.4 42.5 ...
 $ BiologicalMaterial01  : num  6.25 8.01 8.01 8.01 7.47 6.12 7.48 6.94 6.94 6.94 ...
 $ BiologicalMaterial02  : num  49.6 61 61 61 63.3 ...
 $ BiologicalMaterial03  : num  57 67.5 67.5 67.5 72.2 ...
 $ ManufacturingProcess01: num  NA 0 0 0 10.7 12 11.5 12 12 12 ...
 $ ManufacturingProcess02: num  NA 0 0 0 0 0 0 0 0 0 ...
 $ ManufacturingProcess03: num  NA NA NA NA NA NA 1.56 1.55 1.56 1.55 ...

summary(CMP_subset$Yield)

   Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
  35.25   38.75   39.97   40.18   41.48   46.34 

display a simple boxplot

boxplot(CMP_subset$Yield)

make it orange and give it a name

boxplot(CMP_subset$Yield, col= "orange", main ="Yield Summary")

display color names range 1:6

colors()[1:6]

[1] "white"         "aliceblue"     "antiquewhite"  "antiquewhite1" "antiquewhite2" "antiquewhite3"

# display color help and examples

?colors
demo(colors)

    demo(colors)
    ---- ~~~~~~

> ### ----------- Show (almost) all named colors ---------------------
> 
> ## 1) with traditional 'graphics' package:
> showCols1 <- function(bg = "gray", cex = 0.75, srt = 30) {
+     m <- ceiling(sqrt(n <- length(cl <- colors())))
+     length(cl) <- m*m; cm <- matrix(cl, m)
+     ##
+     require("graphics")
+     op <- par(mar=rep(0,4), ann=FALSE, bg = bg); on.exit(par(op))
+     plot(1:m,1:m, type="n", axes=FALSE)
+     text(col(cm), rev(row(cm)), cm,  col = cl, cex=cex, srt=srt)
+ }

> showCols1()

> ## 2) with 'grid' package:
> showCols2 <- function(bg = "grey", cex = 0.75, rot = 30) {
+     m <- ceiling(sqrt(n <- length(cl <- colors())))
+     length(cl) <- m*m; cm <- matrix(cl, m)
+     ##
+     require("grid")
+     grid.newpage(); vp <- viewport(w = .92, h = .92)
+     grid.rect(gp=gpar(fill=bg))
+     grid.text(cm, x = col(cm)/m, y = rev(row(cm))/m, rot = rot,
+               vp=vp, gp=gpar(cex = cex, col = cm))
+ }

> showCols2()

> showCols2(bg = "gray33")

> ###
> 
> ##' @title Comparing Colors
> ##' @param col
> ##' @param nrow
> ##' @param ncol
> ##' @param txt.col
> ##' @return the grid layout, invisibly
> ##' @author Marius Hofert, originally
> plotCol <- function(col, nrow=1, ncol=ceiling(length(col) / nrow),
+                     txt.col="black") {
+     stopifnot(nrow >= 1, ncol >= 1)
+     if(length(col) > nrow*ncol)
+         warning("some colors will not be shown")
+     require(grid)
+     grid.newpage()
+     gl <- grid.layout(nrow, ncol)
+     pushViewport(viewport(layout=gl))
+     ic <- 1
+     for(i in 1:nrow) {
+         for(j in 1:ncol) {
+             pushViewport(viewport(layout.pos.row=i, layout.pos.col=j))
+             grid.rect(gp= gpar(fill=col[ic]))
+             grid.text(col[ic], gp=gpar(col=txt.col))
+             upViewport()
+             ic <- ic+1
+         }
+     }
+     upViewport()
+     invisible(gl)
+ }

> ## A Chocolate Bar of colors:
> plotCol(c("#CC8C3C", paste0("chocolate", 2:4),
+           paste0("darkorange", c("",1:2)), paste0("darkgoldenrod", 1:2),
+           "orange", "orange1", "sandybrown", "tan1", "tan2"),
+         nrow=2)

> ##' Find close R colors() to a given color {original by Marius Hofert)
> ##' using Euclidean norm in (HSV / RGB / ...) color space
> nearRcolor <- function(rgb, cSpace = c("hsv", "rgb255", "Luv", "Lab"),
+                        dist = switch(cSpace, "hsv" = 0.10, "rgb255" = 30,
+                        "Luv" = 15, "Lab" = 12))
+ {
+     if(is.character(rgb)) rgb <- col2rgb(rgb)
+     stopifnot(length(rgb <- as.vector(rgb)) == 3)
+     Rcol <- col2rgb(.cc <- colors())
+     uniqC <- !duplicated(t(Rcol)) # gray9 == grey9 (etc)
+     Rcol <- Rcol[, uniqC] ; .cc <- .cc[uniqC]
+     cSpace <- match.arg(cSpace)
+     convRGB2 <- function(Rgb, to)
+         t(convertColor(t(Rgb), from="sRGB", to=to, scale.in=255))
+     ## the transformation,  rgb{0..255} --> cSpace :
+     TransF <- switch(cSpace,
+                      "rgb255" = identity,
+                      "hsv" = rgb2hsv,
+                      "Luv" = function(RGB) convRGB2(RGB, "Luv"),
+                      "Lab" = function(RGB) convRGB2(RGB, "Lab"))
+     d <- sqrt(colSums((TransF(Rcol) - as.vector(TransF(rgb)))^2))
+     iS <- sort.list(d[near <- d <= dist])# sorted: closest first
+     setNames(.cc[near][iS], format(zapsmall(d[near][iS]), digits=3))
+ }

> nearRcolor(col2rgb("tan2"), "rgb")
         0.0         21.1         25.8         29.5 
      "tan2"       "tan1" "sandybrown"    "sienna1" 

> nearRcolor(col2rgb("tan2"), "hsv")
      0.0000       0.0410       0.0618       0.0638       0.0667       0.0766       0.0778 
      "tan2"    "sienna2"     "coral2"    "tomato2"       "tan1"      "coral"    "sienna1" 
      0.0900       0.0912       0.0918 
"sandybrown"     "coral1"     "tomato" 

> nearRcolor(col2rgb("tan2"), "Luv")
        0.00         7.42         7.48        12.41        13.69 
      "tan2"       "tan1" "sandybrown"    "orange3"    "orange2" 

> nearRcolor(col2rgb("tan2"), "Lab")
        0.00         5.56         8.08        11.31 
      "tan2"       "tan1" "sandybrown"       "peru" 

> nearRcolor("#334455")
         0.0867 
"darkslategray" 

> ## Now, consider choosing a color by looking in the
> ## neighborhood of one you know :
> 
> plotCol(nearRcolor("deepskyblue", "rgb", dist=50))

> plotCol(nearRcolor("deepskyblue", dist=.1))

> plotCol(nearRcolor("tomato", "rgb", dist= 50), nrow=3)

> plotCol(nearRcolor("tomato", "hsv", dist=.12), nrow=3)

> plotCol(nearRcolor("tomato", "Luv", dist= 25), nrow=3)

> plotCol(nearRcolor("tomato", "Lab", dist= 18), nrow=3)

get random set of color set

set.seed(2)
n_cols = ncol(CMP_subset)
col_sample = sample(colors(), n_cols)
col_sample

[1] "lightgray"      "lavenderblush4" "grey12"         "grey88"         "gray51"        
[6] "ivory4"         "grey36"        

use colors in boxplot

boxplot(CMP_subset, col = col_sample)

display histogram data without plotting

hist(CMP_subset$Yield, plot = F)

$breaks
 [1] 35 36 37 38 39 40 41 42 43 44 45 46 47

$counts
 [1]  1  3 16 31 39 32 21 20 10  2  0  1

$density
 [1] 0.005681818 0.017045455 0.090909091 0.176136364 0.221590909 0.181818182 0.119318182 0.113636364
 [9] 0.056818182 0.011363636 0.000000000 0.005681818

$mids
 [1] 35.5 36.5 37.5 38.5 39.5 40.5 41.5 42.5 43.5 44.5 45.5 46.5

$xname
[1] "CMP_subset$Yield"

$equidist
[1] TRUE

attr(,"class")
[1] "histogram"

plotting histogram with vector of sample colors with x-axis and title changed

hist(CMP_subset$Yield, col=col_sample[1:3], xlab = "Yield", main = "Dist. of Yield" )

using par(mfrow = c(x,x)) to designate the the layout of the below histograms

par(mfrow = c(1,2))
hist(CMP_subset$BiologicalMaterial01, col=col_sample[2], xlab = "Bio Material 1", main = "Dist. of Bio Material 1")
hist(CMP_subset$BiologicalMaterial02, col=col_sample[3], xlab = "Bio Material 2", main = "Dist. of Bio Material 2")

display three histograms in dataframe view of 1 row, 3 columns

par(mfrow = c(1,3))
hist(CMP_subset$BiologicalMaterial01, col=col_sample[2], xlab = "Bio Material 1", main = "Dist. of Bio Material 1")
hist(CMP_subset$BiologicalMaterial02, col=col_sample[3], xlab = "Bio Material 2", main = "Dist. of Bio Material 2")

hist(CMP_subset$BiologicalMaterial03, col=col_sample[4], xlab = "Bio Material 3", main = "Dist. of Bio Material 3")

creat plot with pch title, x/y-axis lables, and pch symbol mod with 2x enlargement, color =steelblue

plot(CMP_subset[,2],CMP_subset[,1], xlab = "Bio Material 1", ylab = "Yield", main = "Bio. Material 1 vs Yield",pch = 4, cex = 2, col ="steelblue")

correlation matrix for quick analysis

pairs(CMP_subset[,1:4], pch=19, col="steelblue")

install/load corrlot package

install.packages("corrplot")

trying URL 'https://cran.rstudio.com/bin/macosx/el-capitan/contrib/3.6/corrplot_0.84.tgz'
Content type 'application/x-gzip' length 5452777 bytes (5.2 MB)
==================================================
downloaded 5.2 MB

The downloaded binary packages are in
    /var/folders/pz/0fvcbrdd2hb75sqqgw0q7thw0000gn/T//RtmpOJSTTK/downloaded_packages

library(corrplot)

corrplot 0.84 loaded

library(help="corrplot")

chart a corrplot on std deviation of 1

CMP_cor = cor(CMP_subset[,1:4])
View(CMP_cor)

render it with a change in vis method

corrplot(CMP_cor, method = "pie")

display mixed corrplot

corrplot.mixed(CMP_cor)

install.packages("ggplot2")

Error in install.packages : Updating loaded packages

library(ggplot2)

?ggplot2

ggp1 = ggplot(CMP_subset, aes(x=Yield))
ggp1

Layered geom_histogram with binwidth 0.75, outline/fill color

ggp1 = ggp1 + geom_histogram(aes(y= ..density..), binwidth = 0.75, color="steelblue", fill="gray")

layer density on top of histogram

ggp1 = ggp1 + geom_density(alpha=.5, color="gray", fill="steelblue")
ggp1  

using labs function to add title and subtitle

ggp1 = ggp1 + labs(title="Distrobution", subtitle="Histogram & Density")
ggp1

ggp2 = ggplot(CMP_subset, aes(x=BiologicalMaterial01, y=Yield))
ggp2

ggp2 = ggp2 + geom_point()
ggp2

ggp2 = ggp2 +
  geom_point(color="darkorange")+
  geom_smooth(method = lm)+
  labs(title="Bio. Material 1 vs Yield", subtitle = "Scatterplot with linear fit")
ggp2

ggtheme1 = theme_bw() + theme(axis.title = element_text(size = 20),
                            axis.text = element_text(size = 16), 
                            plot.title = element_text(size = 25), 
                            plot.subtitle = element_text(size = 18))

ggp2 = ggp2 + ggtheme1
ggp2